Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters

David G. Jones and Jitendra Malik

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-91-655
October 1991

http://www.eecs.berkeley.edu/Pubs/TechRpts/1991/CSD-91-655.pdf

We present a computational framework for stereopsis based on the outputs of linear spatial filters tuned to a range of orientations and scales. This approach goes beyond edge-based and area-based approaches by using a richer image description and incorporating several stereo cues that previously have been neglected in the computer vision literature.

A technique based on using the pseudo-inverse is presented for characterizing the information present in a vector of filter responses. We show how in our framework viewing geometry can be recovered to determine the locations of epipolar lines. An assumption that visible surfaces in the scene are piecewise smooth leads to differential treatment of image regions corresponding to binocularly visible surfaces, surface boundaries, and occluded regions that are only monocularly visible. The constraints imposed by viewing geometry and piecewise smoothness are incorporated into an iterative algorithm that gives good results on random-dot stereograms, artificially generated scenes, and natural grey-level images.


BibTeX citation:

@techreport{Jones:CSD-91-655,
    Author = {Jones, David G. and Malik, Jitendra},
    Title = {A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {1991},
    Month = {Oct},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1991/5784.html},
    Number = {UCB/CSD-91-655},
    Abstract = {We present a computational framework for stereopsis based on the outputs of linear spatial filters tuned to a range of orientations and scales. This approach goes beyond edge-based and area-based approaches by using a richer image description and incorporating several stereo cues that previously have been neglected in the computer vision literature. <p>A technique based on using the pseudo-inverse is presented for characterizing the information present in a vector of filter responses. We show how in our framework viewing geometry can be recovered to determine the locations of epipolar lines. An assumption that visible surfaces in the scene are piecewise smooth leads to differential treatment of image regions corresponding to binocularly visible surfaces, surface boundaries, and occluded regions that are only monocularly visible. The constraints imposed by viewing geometry and piecewise smoothness are incorporated into an iterative algorithm that gives good results on random-dot stereograms, artificially generated scenes, and natural grey-level images.}
}

EndNote citation:

%0 Report
%A Jones, David G.
%A Malik, Jitendra
%T A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters
%I EECS Department, University of California, Berkeley
%D 1991
%@ UCB/CSD-91-655
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/1991/5784.html
%F Jones:CSD-91-655